微阵列癌症数据误标记样本和异常样本识别的广义CL-stability算法

微阵列癌症数据误标记样本和异常样本识别的广义CL-stability算法

周柚, 张琛, 吴春国, 时小虎, 梁艳春

吉林大学计算机科学与技术学院, 长春 130012

收稿日期:2008-03-23 修回日期:1900-01-01 出版日期:2008-05-26 发布日期:2008-05-26
通讯作者: 梁艳春

Generalized CL-stability Algorithm for Recognition on Mislabeled and Abnormal Samples in Cancer Microarray

ZHOU You, ZHANG Chen, WU Chunguo, SHI Xiaohu, LIANG Yanchu

College of Computer Science and Technology, Jilin University, Changchun 130012, China

Received:2008-03-23 Revised:1900-01-01 Online:2008-05-26 Published:2008-05-26
Contact: LIANG Yanchu

摘要/Abstract

摘要： 针对微阵列癌症数据的特点, 提出一种能识别数据集中误标记样本和异常样本的广义CLstability算法. 该算法以CL-stability为基本算子, 通过样本的全局稳定性识别误标记样本或异常样本. 实验结果表明, 广义CL-stability算法对于识别微阵列癌症数据中的误标记样本优于已有算法, 并能给出区分误标记样本和异常样本的信息.

关键词: 误标记样本识别, 异常样本识别, 微阵列, 广义CLstability算法

Abstract: A generalized CL-stability algorithm proposed in this paper can be used to recognize mislabeled samples and abnormal samples in cancer microarray. The CL-stability is selected as a basic operator in the proposed a lgorithm. The mislabeled samples or abnormal samples are detected depending on the gobal stability of samples. Experimental results show that the generalized CL-stability algorithm is not only better than other existing algorithms, but also used to distinguish mislabeled samples and abnormal samples.

Key words: mislabeled sample recognition, abnormal sample recognition, microarray, generalized CL-stability algorithm

中图分类号:

TP183

周柚, 张琛, 吴春国, 时小虎, 梁艳春. 微阵列癌症数据误标记样本和异常样本识别的广义CL-stability算法[J]. J4, 2008, 46(03): 509-511.

ZHOU You, ZHANG Chen, WU Chunguo, SHI Xiaohu, LIANG Yanchu. Generalized CL-stability Algorithm for Recognition on Mislabeled and Abnormal Samples in Cancer Microarray[J]. J4, 2008, 46(03): 509-511.